This repository is a curated list of academic papers focused on learning for humanoid robots, prioritizing real-world experiments and open-source code. It serves researchers and engineers in robotics, AI, and computer vision seeking to advance humanoid robot capabilities in areas like locomotion, manipulation, and whole-body control. The collection aims to provide a comprehensive overview of the state-of-the-art and facilitate the adoption of advanced learning techniques in humanoid robotics.

How It Works

The list categorizes papers by task focus, including Loco-Manipulation, Whole-Body Control, Manipulation, Teleoperation, Locomotion, and Simulation. It highlights papers with real robot experiments and marks those with open-sourced code with a star (🌟). The collection is actively maintained through pull requests, encouraging community contributions to keep it up-to-date with the latest research.

Quick Start & Requirements

This is a curated list of papers and does not have a direct installation or execution command. Users are expected to access the linked papers (primarily arXiv) and their associated codebases individually.

Highlighted Details

• Extensive coverage of recent (2024-2025) research in humanoid robot learning.
• Strong emphasis on papers with real-world experiments and open-source code.
• Categorization by key humanoid robot tasks, facilitating targeted research.
• Inclusion of papers related to simulation, hardware design, and benchmarks.

Maintenance & Community

The repository is maintained by Yanjie Ze, with an open invitation for community contributions via pull requests. Contact information for suggestions is provided.

Licensing & Compatibility

The repository itself is likely under a permissive license (e.g., MIT, Apache 2.0, common for "awesome" lists), but the licensing of the individual papers and their associated codebases varies and must be checked on a per-item basis.

Limitations & Caveats

This is a bibliography and not a software library; it does not provide any executable code or integrated framework. Users must independently locate and evaluate each paper and its associated code. The quality and availability of linked resources are not guaranteed by this repository.